Re-enter in-flight work in a fresh session by reading a resume block a previous session left (the read half of the handoff/pickup loop). Use at the start of a fresh session, or when the user says "pickup", "resume", "이어서", "재개", "어디까지 했지", "continue where we left off".
Scanned 9/6/2026
Install to Claude Code
npx -y skills add jhlee0409/omni-harness-kit --skill pickup --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Pickup?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/jhlee0409-pickup)More formats (shields.io, HTML) on the badges page.
---
name: pickup
description: >-
Re-enter in-flight work in a fresh session by reading a resume block a previous
session left (the read half of the handoff/pickup loop). Use at the start of a
fresh session, or when the user says "pickup", "resume", "이어서", "재개",
"어디까지 했지", "continue where we left off".
argument-hint: "[spec-slug]"
allowed-tools: Read, Bash, Grep, Glob
---
# pickup
Re-establish where the work left off — from the resume block ALONE, without asking
the user to re-narrate.
1. **Find the resume block.** Prefer an active spec's `specs/*/context.md`
`## 0. Resume here` block (use the `[spec-slug]` arg to disambiguate when several
exist) — that is where `/harness-kit:handoff` writes when a spec is active; fall
back to `.claude/handoff.md`. When both exist, use the most recently modified —
it is the freshest handoff. If none is found, say so plainly — don't guess.
2. **Read it fully**, then re-ground in the repo: `git status --short`,
`git log --oneline -5`, and read the files it lists. Confirm the stated state
matches reality (files actually changed, the next command still makes sense).
3. **Restate** the original ask + where you are (phase / N of M) + the single next
action — then DO that next action. Do NOT redo the "Don't redo" items.
4. If the block contradicts the repo (says a file was changed but it wasn't),
surface the conflict instead of trusting the block blindly.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.